ClawHub
Back to skill

Security audit

EmpirioLabs AI Models

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward public model-catalog lookup helper that makes disclosed read-only requests to EmpirioLabs and does not handle credentials or persist anything.

Install only if you are comfortable with the agent querying EmpirioLabs' public catalog when you ask for model and pricing information. No API key is needed for this lookup skill, but related EmpirioLabs generation skills may require credentials separately.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill explicitly requires network access and instructs the user to query a live external catalog, but it does not declare any tool scope such as allowed hosts or permissions. That creates an authorization gap where the runtime may permit broader outbound access than intended, increasing the risk of unintended data transmission or SSRF-like misuse if the referenced scripts are modified or repurposed.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

md
python3 models.py --categories
  python3 models.py --category video --json

Reads GET https://api.empiriolabs.ai/v1/models, which is public: no API key is needed.
Python 3.8+, standard library only.
"""

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/models.py (reported line 13)May include surrounding context.

python
python3 models.py --categories
  python3 models.py --category video --json

Reads GET https://api.empiriolabs.ai/v1/models, which is public: no API key is needed.
Python 3.8+, standard library only.
"""

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/models.py (reported line 30)May include surrounding context.

python
python3 models.py --categories
  python3 models.py --category video --json

Reads GET https://api.empiriolabs.ai/v1/models, which is public: no API key is needed.
Python 3.8+, standard library only.
"""

Static analysis

No suspicious patterns detected.